stanford-cs231 and cs231n-convolutional-neural-networks-solutions
The resources are complementary, with one providing study materials and guidance for a course, and the other offering assignment solutions for the same course.
About stanford-cs231
machinelearningnanodegree/stanford-cs231
Resources for students in the Udacity's Machine Learning Engineer Nanodegree to work through Stanford's Convolutional Neural Networks for Visual Recognition course (CS231n).
This project provides a curated set of resources to help you learn about Convolutional Neural Networks for visual recognition. It brings together course materials like lectures, assignments, and notes from Stanford's CS231n, along with supplementary blogs and articles. It's for students enrolled in Udacity's Machine Learning Engineer Nanodegree or anyone looking to deepen their understanding of how computers 'see' and interpret images.
About cs231n-convolutional-neural-networks-solutions
madalinabuzau/cs231n-convolutional-neural-networks-solutions
Assignment solutions for the CS231n course taught by Stanford on visual recognition. Spring 2017 solutions are for both deep learning frameworks: TensorFlow and PyTorch.
This provides completed assignments for the Stanford CS231n course on visual recognition, helping students learn to build and train convolutional neural networks. You get structured problem sets and their solutions, which demonstrate how to implement deep learning models using TensorFlow and PyTorch. This is ideal for students or self-learners taking the CS231n course or similar deep learning programs.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work